{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.03469210754553339,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.003469210754553339,
      "grad_norm": 7.699210166931152,
      "learning_rate": 2e-05,
      "loss": 51.4533,
      "step": 1
    },
    {
      "epoch": 0.006938421509106678,
      "grad_norm": 15.918562889099121,
      "learning_rate": 4e-05,
      "loss": 51.817,
      "step": 2
    },
    {
      "epoch": 0.010407632263660017,
      "grad_norm": 14.194038391113281,
      "learning_rate": 6e-05,
      "loss": 52.3584,
      "step": 3
    },
    {
      "epoch": 0.010407632263660017,
      "eval_loss": 13.009323120117188,
      "eval_runtime": 6.9443,
      "eval_samples_per_second": 17.568,
      "eval_steps_per_second": 8.784,
      "step": 3
    },
    {
      "epoch": 0.013876843018213356,
      "grad_norm": 14.6574125289917,
      "learning_rate": 8e-05,
      "loss": 52.6486,
      "step": 4
    },
    {
      "epoch": 0.017346053772766695,
      "grad_norm": 15.214132308959961,
      "learning_rate": 0.0001,
      "loss": 51.567,
      "step": 5
    },
    {
      "epoch": 0.020815264527320035,
      "grad_norm": 17.45503044128418,
      "learning_rate": 0.00012,
      "loss": 51.1741,
      "step": 6
    },
    {
      "epoch": 0.020815264527320035,
      "eval_loss": 12.606266021728516,
      "eval_runtime": 7.5328,
      "eval_samples_per_second": 16.196,
      "eval_steps_per_second": 8.098,
      "step": 6
    },
    {
      "epoch": 0.024284475281873375,
      "grad_norm": 19.02105712890625,
      "learning_rate": 0.00014,
      "loss": 50.1376,
      "step": 7
    },
    {
      "epoch": 0.027753686036426712,
      "grad_norm": 13.59460735321045,
      "learning_rate": 0.00016,
      "loss": 49.2638,
      "step": 8
    },
    {
      "epoch": 0.031222896790980052,
      "grad_norm": 9.423663139343262,
      "learning_rate": 0.00018,
      "loss": 48.7117,
      "step": 9
    },
    {
      "epoch": 0.031222896790980052,
      "eval_loss": 12.042184829711914,
      "eval_runtime": 7.0052,
      "eval_samples_per_second": 17.416,
      "eval_steps_per_second": 8.708,
      "step": 9
    },
    {
      "epoch": 0.03469210754553339,
      "grad_norm": 3.8764379024505615,
      "learning_rate": 0.0002,
      "loss": 48.122,
      "step": 10
    }
  ],
  "logging_steps": 1,
  "max_steps": 10,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 3,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 381542706708480.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}